arXiv subjects

Lihi Zelnik-Manor

Publications and source records attributed to Lihi Zelnik-Manor.

30 records · Page 2Linked to original sources

arXiv2019

The 2018 PIRM Challenge on Perceptual Image Super-resolution

This paper reports on the 2018 PIRM challenge on perceptual super-resolution (SR), held in conjunction with the Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018. In contrast to previous SR challenges, our evaluation methodology jointly quantifies accuracy and perceptual quality, therefore enabling perceptual-driven methods to compete alongside algorithms that target PSNR maximization. Twenty-one participating teams introduced algorithms which well-improved upon the existing state-of-the-art methods in perceptual SR, as confirmed by a human opinion study. We also analyze popular image quality measures and draw conclusions regarding which of them correlates best with human opinion scores. We conclude with an analysis of the current trends in perceptual SR, as reflected from the leading submissions.

cs.CV↗

arXiv2019

Is Image Memorability Prediction Solved?

This paper deals with the prediction of the memorability of a given image. We start by proposing an algorithm that reaches human-level performance on the LaMem dataset - the only large scale benchmark for memorability prediction. The suggested algorithm is based on three observations we make regarding convolutional neural networks (CNNs) that affect memorability prediction. Having reached human-level performance we were humbled, and asked ourselves whether indeed we have resolved memorability prediction - and answered this question in the negative. We studied a few factors and made some recommendations that should be taken into account when designing the next benchmark.

cs.CV↗

arXiv2018

Adversarial Feedback Loop

Thanks to their remarkable generative capabilities, GANs have gained great popularity, and are used abundantly in state-of-the-art methods and applications. In a GAN based model, a discriminator is trained to learn the real data distribution. To date, it has been used only for training purposes, where it's utilized to train the generator to provide real-looking outputs. In this paper we propose a novel method that makes an explicit use of the discriminator in test-time, in a feedback manner in order to improve the generator results. To the best of our knowledge it is the first time a discriminator is involved in test-time. We claim that the discriminator holds significant information on the real data distribution, that could be useful for test-time as well, a potential that has not been explored before. The approach we propose does not alter the conventional training stage. At test-time, however, it transfers the output from the generator into the discriminator, and uses feedback modules (convolutional blocks) to translate the features of the discriminator layers into corrections to the features of the generator layers, which are used eventually to get a better generator result. Our method can contribute to both conditional and unconditional GANs. As demonstrated by our experiments, it can improve the results of state-of-the-art networks for super-resolution, and image generation.

cs.CV↗

arXiv2018

The Contextual Loss for Image Transformation with Non-Aligned Data

Feed-forward CNNs trained for image transformation problems rely on loss functions that measure the similarity between the generated image and a target image. Most of the common loss functions assume that these images are spatially aligned and compare pixels at corresponding locations. However, for many tasks, aligned training pairs of images will not be available. We present an alternative loss function that does not require alignment, thus providing an effective and simple solution for a new space of problems. Our loss is based on both context and semantics -- it compares regions with similar semantic meaning, while considering the context of the entire image. Hence, for example, when transferring the style of one face to another, it will translate eyes-to-eyes and mouth-to-mouth. Our code can be found at https://www.github.com/roimehrez/contextualLoss

cs.CV↗

arXiv2018

Maintaining Natural Image Statistics with the Contextual Loss

Maintaining natural image statistics is a crucial factor in restoration and generation of realistic looking images. When training CNNs, photorealism is usually attempted by adversarial training (GAN), that pushes the output images to lie on the manifold of natural images. GANs are very powerful, but not perfect. They are hard to train and the results still often suffer from artifacts. In this paper we propose a complementary approach, that could be applied with or without GAN, whose goal is to train a feed-forward CNN to maintain natural internal statistics. We look explicitly at the distribution of features in an image and train the network to generate images with natural feature distributions. Our approach reduces by orders of magnitude the number of images required for training and achieves state-of-the-art results on both single-image super-resolution, and high-resolution surface normal estimation.

cs.CV↗

arXiv2018

Saliency Driven Image Manipulation

Have you ever taken a picture only to find out that an unimportant background object ended up being overly salient? Or one of those team sports photos where your favorite player blends with the rest? Wouldn't it be nice if you could tweak these pictures just a little bit so that the distractor would be attenuated and your favorite player will stand-out among her peers? Manipulating images in order to control the saliency of objects is the goal of this paper. We propose an approach that considers the internal color and saliency properties of the image. It changes the saliency map via an optimization framework that relies on patch-based manipulation using only patches from within the same image to achieve realistic looking results. Applications include object enhancement, distractors attenuation and background decluttering. Comparing our method to previous ones shows significant improvement, both in the achieved saliency manipulation and in the realistic appearance of the resulting images.

cs.CV↗

arXiv2017

Photorealistic Style Transfer with Screened Poisson Equation

Recent work has shown impressive success in transferring painterly style to images. These approaches, however, fall short of photorealistic style transfer. Even when both the input and reference images are photographs, the output still exhibits distortions reminiscent of a painting. In this paper we propose an approach that takes as input a stylized image and makes it more photorealistic. It relies on the Screened Poisson Equation, maintaining the fidelity of the stylized image while constraining the gradients to those of the original input image. Our method is fast, simple, fully automatic and shows positive progress in making a stylized image photorealistic. Our results exhibit finer details and are less prone to artifacts than the state-of-the-art.

cs.CV↗

arXiv2017

Template Matching with Deformable Diversity Similarity

We propose a novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template. We rely on both local appearance and geometric information that jointly lead to a powerful approach for matching. Our key contribution is a similarity measure, that is robust to complex deformations, significant background clutter, and occlusions. Empirical evaluation on the most up-to-date benchmark shows that our method outperforms the current state-of-the-art in its detection accuracy while improving computational complexity.

cs.CV↗

arXiv2015

Approximate Nearest Neighbor Fields in Video

We introduce RIANN (Ring Intersection Approximate Nearest Neighbor search), an algorithm for matching patches of a video to a set of reference patches in real-time. For each query, RIANN finds potential matches by intersecting rings around key points in appearance space. Its search complexity is reversely correlated to the amount of temporal change, making it a good fit for videos, where typically most patches change slowly with time. Experiments show that RIANN is up to two orders of magnitude faster than previous ANN methods, and is the only solution that operates in real-time. We further demonstrate how RIANN can be used for real-time video processing and provide examples for a range of real-time video applications, including colorization, denoising, and several artistic effects.

cs.CV↗

arXiv2012

Crowdsourcing Gaze Data Collection

Knowing where people look is a useful tool in many various image and video applications. However, traditional gaze tracking hardware is expensive and requires local study participants, so acquiring gaze location data from a large number of participants is very problematic. In this work we propose a crowdsourced method for acquisition of gaze direction data from a virtually unlimited number of participants, using a robust self-reporting mechanism (see Figure 1). Our system collects temporally sparse but spatially dense points-of-attention in any visual information. We apply our approach to an existing video data set and demonstrate that we obtain results similar to traditional gaze tracking. We also explore the parameter ranges of our method, and collect gaze tracking data for a large set of YouTube videos.

cs.SI↗

arXiv2010

Sensing Matrix Optimization for Block-Sparse Decoding

Recent work has demonstrated that using a carefully designed sensing matrix rather than a random one, can improve the performance of compressed sensing. In particular, a well-designed sensing matrix can reduce the coherence between the atoms of the equivalent dictionary, and as a consequence, reduce the reconstruction error. In some applications, the signals of interest can be well approximated by a union of a small number of subspaces (e.g., face recognition and motion segmentation). This implies the existence of a dictionary which leads to block-sparse representations. In this work, we propose a framework for sensing matrix design that improves the ability of block-sparse approximation techniques to reconstruct and classify signals. This method is based on minimizing a weighted sum of the inter-block coherence and the sub-block coherence of the equivalent dictionary. Our experiments show that the proposed algorithm significantly improves signal recovery and classification ability of the Block-OMP algorithm compared to sensing matrix optimization methods that do not employ block structure.

cs.IT↗

arXiv2010

Dictionary Optimization for Block-Sparse Representations

Recent work has demonstrated that using a carefully designed dictionary instead of a predefined one, can improve the sparsity in jointly representing a class of signals. This has motivated the derivation of learning methods for designing a dictionary which leads to the sparsest representation for a given set of signals. In some applications, the signals of interest can have further structure, so that they can be well approximated by a union of a small number of subspaces (e.g., face recognition and motion segmentation). This implies the existence of a dictionary which enables block-sparse representations of the input signals once its atoms are properly sorted into blocks. In this paper, we propose an algorithm for learning a block-sparsifying dictionary of a given set of signals. We do not require prior knowledge on the association of signals into groups (subspaces). Instead, we develop a method that automatically detects the underlying block structure. This is achieved by iteratively alternating between updating the block structure of the dictionary and updating the dictionary atoms to better fit the data. Our experiments show that for block-sparse data the proposed algorithm significantly improves the dictionary recovery ability and lowers the representation error compared to dictionary learning methods that do not employ block structure.

cs.IT↗